Enterprise-Multi-AI-Agent-Systems-
🤖 Build and deploy scalable Multi-AI Agent systems with LangGraph and Groq LLMs to enhance intelligence across enterprise applications.
claude mcp add --transport stdio omri3193-enterprise-multi-ai-agent-systems- python -m enterprise_multi_ai_agent_systems \ --env AWS_REGION="Optional: AWS region for ECS/Fargate deployment" \ --env SECRET_KEY="Optional: secret key for app security" \ --env DATABASE_URL="Optional: database connection string" \ --env FASTAPI_PORT="Optional: port number for FastAPI server (default 8000)" \ --env TAVILY_API_KEY="Your real-time web search API key"
How to use
Enterprise-Multi-AI-Agent-Systems provides a framework to deploy and manage multiple AI agents that can perform tasks concurrently. Agents can be configured with real-time web search capabilities via the Tavily API, enabling live information retrieval during task execution. The system is designed around a FastAPI-based service that coordinates agent creation, task assignment, and performance monitoring. Use the included dashboard to create new agents, set priorities, and observe progress metrics such as task completion rates. When running on AWS ECS Fargate, the platform can scale horizontally to support a larger number of agents or higher workloads. This makes it suitable for complex automation workflows, research tasks, or enterprise-grade automation pipelines.
How to install
Prerequisites:
- Python 3.8+ installed on the host
- Git available to clone the repository
- Optional: virtual environment tool (venv) for isolation
-
Clone the repository: git clone https://github.com/omri3193/Enterprise-Multi-AI-Agent-Systems-.git cd Enterprise-Multi-AI-Agent-Systems-
-
Create and activate a virtual environment (recommended): python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install dependencies: pip install -r requirements.txt
-
Configure environment variables (example): export TAVILY_API_KEY=your-tavily-api-key export DATABASE_URL=postgresql://user:pass@host:port/dbname export SECRET_KEY=your-secret-key
-
Run the application (development): python -m enterprise_multi_ai_agent_systems
-
Optional: run with a production server (example using uvicorn): uvicorn enterprise_multi_ai_agent_systems.app:app --host 0.0.0.0 --port 8000
Notes:
- If you are deploying on AWS ECS Fargate, containerize the app and configure the service according to your cluster setup.
- Ensure network access to the Tavily API and any data stores you use.
Additional notes
Tips and common issues:
- Ensure your Tavily API key is valid; without it, real-time web search features will be unavailable.
- When running behind a corporate proxy, set HTTP(S)_PROXY environment variables so the app can fetch external resources.
- If you change the port, update FASTAPI_PORT in the environment and ensure security groups allow the chosen port.
- For production deployments, consider setting a persistent database URL and a secure SECRET_KEY.
- Monitor resource usage (CPU/RAM) as multiple agents run concurrently; scale your ECS Fargate task definitions accordingly.
Related MCP Servers
dify
Production-ready platform for agentic workflow development.
ruflo
🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration
superset
IDE for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine
solace-agent-mesh
An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows.
agentic-radar
A security scanner for your LLM agentic workflows
codexia
Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control